A
licenseNot graded
qualityA
maintenanceEnables coding agents to publish HTML artifacts that users can review and comment on in a sandboxed browser viewer, with feedback loop support for iterative versions.
11 npm
MIT
Terrarium
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Terrariumpublish the new pricing page for feedback"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Terrarium plugin for Claude Code
Give your agent a place to show its work to humans. Terrarium hosts the HTML your agent builds; humans review it in the browser with comments anchored to exact passages; the agent pulls that feedback over MCP, pushes fixes, and repeats until approved.
Install
/plugin marketplace add nelsonsantryhkd/terrarium-plugin
/plugin install terrarium@terrariumThen mint a token at tryterrarium.com/connect
and make it available as TERRARIUM_PAT:
export TERRARIUM_PAT="samus_pat_…"(Or just ask your agent to set Terrarium up — the bundled skill walks it through the whole flow, including sending you to /connect for the token.)
Related MCP server: Pingfusi
What it ships
MCP server (
.mcp.json) — Terrarium's remote server over Streamable HTTP with 7 tools:list_artifacts,publish_artifact,get_artifact,pull_comments,push_version,reply_to_comment,resolve_comment.Skill (
skills/terrarium/) — teaches the publish → review → fix loop, including theterrarium-feedback/1payload,expectedVersionfreshness, and comment-thread etiquette.
The protocol
pull_comments returns a versioned, structured payload
(terrarium-feedback/1) designed to be stable enough to build agents against:
review state, typed comment threads (change_request / question / bug),
text anchors with live resolution status, and reply chains. Evolution within
/1 is additive-only.
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessUnresponsive
Related MCP Connectors
Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.
Agents publish self-contained HTML to a stable review link, with page-level feedback and revoke.
Versioned artifact review for people and AI agents, with contextual comments and human control.
MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to publish work mid-task for real human review, collect pinned comments and verdicts, and iterate until the output is approved. It supports second opinions and human judgment on artifacts such as sites, videos, and text.38 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to publish work mid-task and request reviews from real human reviewers, who attach pinned comments and return a verdict so the agent can iterate until approved.38 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to publish their work mid-task and hand it to a real human reviewer, who pins comments to the exact elements that are off and returns an approval verdict. The agent then iterates on that human feedback until the work is signed off.38 npmMIT